© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43608
    Prev
    Next
    INDEX
    Explanations

    responses, views, elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     niedersachsen
    -2.09
    很多的
    -1.88
    関連リンク
    -1.74
    国家的
    -1.70
    籥
    -1.68
    大概是
    -1.67
     vôtre
    -1.66
    ブログ村
    -1.66
     Что
    -1.65
    女孩子
    -1.65
    POSITIVE LOGITS
    ↵↵
    1.98
     is
    1.69
    .
    1.58
    ₤
    1.52
    ↵
    1.51
    "]
    1.46
    )
    1.41
    '],
    1.38
     pentru
    1.34
    ☑️
    1.34
    Activations Density 0.001%

    No Known Activations